add_fact

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden for behavioral disclosure. 'Attach a durable fact' implies persistence and mutation but doesn't state whether it appends, overwrites, or requires existing person records. It doesn't disclose idempotency, conflict behavior, or what 'durable' means relative to other storing tools. The ambiguity-checking instruction is a behavioral note but too shallow to constitute real transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One short sentence plus an instruction fragment. It is efficient and front-loaded with the core purpose. However, the 'Ask the user if the name is ambiguous' fragment is oddly placed and could be integrated more clearly as a usage guideline.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 6 parameters, no annotations, and a low-coverage schema, so the description must compensate for that complexity, but it does not. An output schema exists, which lowers the burden for explaining return values, but the description still leaves major gaps: what 'durable fact' entails, how person_name disambiguation works, and parameter semantics are all unexplained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain the parameters. It provides essentially zero parameter information — no explanation of how key/value/number/fact_date/confidence relate, which are optional, or what fields are needed for a complete fact. With 6 parameters at 0% coverage, the description's failure to describe any of them is a significant gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states it attaches a durable fact to a person, giving a specific verb and resource. However, the phrase 'Ask the user if the name is ambiguous' confuses the purpose — it reads as an instruction to the agent about conversation behavior rather than clarifying what the tool does. It lacks the behavioral specificity needed to distinguish it from siblings like remember_person or record_interaction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. There's no mention of when a fact should be stored via this tool rather than via remember_person or record_interaction. The 'ask the user if the name is ambiguous' hint gives a minor usage signal but is vague and doesn't establish exclusions or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.